# Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNIST

arXiv: https://arxiv.org/abs/2604.06017 · HTML: https://mlsanity.com/paper/2604.06017/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Disentangling the Factors of Convergence between Brains and Computer Vision Models](https://mlsanity.com/paper/2508.18226/) (2025)
- [Interactive Medical Image Analysis with Concept-based Similarity Reasoning](https://mlsanity.com/paper/2503.06873/) (2025)
- [Representation Potentials of Foundation Models for Multimodal Alignment: A Survey](https://mlsanity.com/paper/2510.05184/) (2025)
- [Rethinking model prototyping through the MedMNIST+ dataset collection](https://mlsanity.com/paper/2404.15786/) (2024)
- [Proof of a perfect platonic representation hypothesis](https://mlsanity.com/paper/2507.01098/) (2025)
- [A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets](https://mlsanity.com/paper/2503.17024/) (2025)
- [Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage](https://mlsanity.com/paper/2510.17833/) (2025)
- [Evaluating the Explainability of Vision Transformers in Medical Imaging](https://mlsanity.com/paper/2510.12021/) (2025)
- [Explaining the Unexplainable: A Systematic Review of Explainable AI in Finance](https://mlsanity.com/paper/2503.05966/) (2025)
- [Medi-CAT: Contrastive Adversarial Training for Medical Image Classification](https://mlsanity.com/paper/2311.00154/) (2023)
- [Explainable AI in Healthcare: to Explain, to Predict, or to Describe?](https://mlsanity.com/paper/2508.05753/) (2025)
- [In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging](https://mlsanity.com/paper/2508.13880/) (2025)
- [Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification](https://mlsanity.com/paper/2207.06975/) (2022)
- [Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification](https://mlsanity.com/paper/2503.14938/) (2025)

## Built on by (most cited first, 2 of 2)

- [Benchmarking PNW Model for MedMNIST to 100% Accuracy](https://mlsanity.com/paper/2604.18916/) (2026)
- [Aristotelian Manifolds: Leveraging Platonic Perceptual Features for Backpropagation Free Rapid Concept Learning](https://mlsanity.com/paper/2608.20682/) (2026)

## Abstract (arXiv)

While deep learning has achieved remarkable success in medical imaging, the "black-box" nature of backpropagation-based models remains a significant barrier to clinical adoption. To bridge this gap, we propose Aristotelian Rapid Object Modeling (A-ROM), a framework built upon the Platonic Representation Hypothesis (PRH). This hypothesis posits that models trained on vast, diverse datasets converge toward a universal and objective representation of reality. By leveraging the generalizable metric space of pretrained Vision Transformers (ViTs), A-ROM enables the rapid modeling of novel medical concepts without the computational burden or opacity of further gradient-based fine-tuning. We replace traditional, opaque decision layers with a human-readable concept dictionary and a k-Nearest Neighbors (kNN) classifier to ensure the model's logic remains interpretable. Experiments on the MedMNIST v2 suite demonstrate that A-ROM delivers performance competitive with standard benchmarks while providing a simple and scalable, "few-shot" solution that meets the rigorous transparency demands of modern clinical environments.